INDEX

Explanations

and

np_max-act · gemini-2.0-flash

This neuron detects mentions of research and development or innovation activities (e.g., discussions of R&D, development, enabling, ensuring, etc.).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iap

-0.06

reating

-0.06

~~~~~~~~~~~~~~~~

-0.06

vection

-0.06

ords

-0.06

apsulation

-0.06

.—

-0.06

urvey

-0.06

 yakın

-0.06

POSITIVE LOGITS

 Duplicate

0.07

 моз

0.07

 Angie

0.06

.turn

0.06

_IDENT

0.06

 polov

0.06

 apply

0.06

 Společ

0.06

(encoded

0.06

 IconButton

0.06

Activations Density 0.034%

and

This neuron detects mentions of research and development or innovation activities (e.g., discussions of R&D, development, enabling, ensuring, etc.).

No Comments

No Known Activations